Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    as followed by imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Appleton
    0.43
     Benson
    0.39
    Suppose
    0.39
    Like
    0.39
     gewe
    0.38
    BooleanField
    0.38
    вань
    0.38
    AUG
    0.37
     Lef
    0.37
    م
    0.37
    POSITIVE LOGITS
     ის
    0.57
    cribable
    0.52
    cribing
    0.49
     it
    0.48
     ाट
    0.46
     evidenced
    0.46
     נ
    0.45
    sembles
    0.45
     _;
    0.45
     as
    0.44
    Act Density 0.011%

    No Known Activations